{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T22:35:29Z","timestamp":1765319729352,"version":"3.46.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"36","license":[{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-025-20913-z","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T06:39:17Z","timestamp":1749019157000},"page":"45267-45295","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A mixed attention-CTC for natural scene text recognition\u2014experienced in Farsi with new presented natural and synthetic dataset"],"prefix":"10.1007","volume":"84","author":[{"given":"Mohammad Mohsen","family":"Talaie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7654-1001","authenticated-orcid":false,"given":"Mohammad Ali","family":"Keyvanrad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Malika","family":"Behroozrazegh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seyyede Mahila","family":"Moghadami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Melika","family":"Sabaghian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"key":"20913_CR1","doi-asserted-by":"crossref","unstructured":"Investigating the challenges and opportunities in persian language information retrieval through standardized data collections and deep learning. [Online]. Available: https:\/\/www.mdpi.com\/2073-431X\/13\/8\/212. Accessed 01 Dec 2024","DOI":"10.3390\/computers13080212"},{"key":"20913_CR2","unstructured":"\"Dissertation: recognition of letters in Persian typed words using morphological method,\" Farsi Scientific Searcher (Elam Net). [Online]. Available: https:\/\/elmnet.ir\/doc\/10017188-2002. Accessed 20 May 2023"},{"key":"20913_CR3","unstructured":"Recognition of Persian printed texts. [Online]. Available: https:\/\/www.virascience.com\/thesis\/14588\/. Accessed 20 May 2023"},{"issue":"8","key":"20913_CR4","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1016\/S0031-3203(99)00114-4","volume":"33","author":"A Amin","year":"2000","unstructured":"Amin A (2000) Recognition of printed arabic text based on global features and decision tree learning techniques. Pattern Recogn 33(8):1309\u20131323. https:\/\/doi.org\/10.1016\/S0031-3203(99)00114-4","journal-title":"Pattern Recogn"},{"issue":"6","key":"20913_CR5","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1016\/S0020-7373(05)80160-9","volume":"35","author":"A Amin","year":"1991","unstructured":"Amin A, Al-Fedaghi S (1991) Machine recognition of printed Arabic text utilizing natural language morphology. Int J Man Mach Stud 35(6):769\u2013788","journal-title":"Int J Man Mach Stud"},{"issue":"5","key":"20913_CR6","doi-asserted-by":"publisher","first-page":"1300","DOI":"10.1109\/21.44052","volume":"19","author":"A Amin","year":"1989","unstructured":"Amin A, Mari JF (1989) Machine recognition and correction of printed Arabic text. IEEE Trans Syst Man Cybern 19(5):1300\u20131306","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"20913_CR7","doi-asserted-by":"crossref","unstructured":"Nawaz SN, Sarfraz M, Zidouri A, Al-Khatib WG (2003) An approach to offline Arabic character recognition using neural networks. In: 10th IEEE international conference on electronics, circuits and systems, 2003. ICECS 2003. Proceedings of the 2003, IEEE, 2003, pp 1328\u20131331","DOI":"10.1109\/ICECS.2003.1301760"},{"key":"20913_CR8","unstructured":"Al-Ateeq HM, Al-Salman AS (2016) Enhancing the segmentation of Arabic characters using baseline information. Int Multiling Acad J\u00a03(1). Available from: https:\/\/www.aasrc.org\/aasrj\/index.php\/imaj\/article\/view\/1805"},{"key":"20913_CR9","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprintarXiv:1409.0473"},{"key":"20913_CR10","unstructured":"Afkari-Fahandari A, Asadi-Zeydabadi F, Shabaninia E, Nezamabadi-pour H. Farsi Handwritten Text Recognition via a Lightweight Attention-driven Sequence Recognition Network. [Online]. Available: https:\/\/www.researchgate.net\/profile\/Ali-Fahandari\/publication\/385283580_Farsi_Handwritten_Text_Recognition_via_a_Lightweight_Attention-driven_Sequence_Recognition_Network\/links\/671dedb5393e8533f71b3df8\/Farsi-Handwritten-Text-Recognition-via-a-Lightweight-Attention-driven-Sequence-Recognition-Network.pdf. Accessed 01 Dec 2024"},{"issue":"22","key":"20913_CR11","doi-asserted-by":"publisher","first-page":"11760","DOI":"10.3390\/app122211760","volume":"12","author":"Z Khosrobeigi","year":"2022","unstructured":"Khosrobeigi Z, Veisi H, Hoseinzade E, Shabanian H (2022) Persian optical character recognition using deep bidirectional long short-term memory. Appl Sci 12(22):11760","journal-title":"Appl Sci"},{"key":"20913_CR12","doi-asserted-by":"crossref","unstructured":"Zhang et al (2024) Self-distillation regularized connectionist temporal classification loss for text recognition: A simple yet effective approach. In: Proceedings of the AAAI conference on artificial intelligence, pp. 7441\u20137449. [Online]. Available: https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/28575. Accessed 01 Dec 2024","DOI":"10.1609\/aaai.v38i7.28575"},{"key":"20913_CR13","doi-asserted-by":"crossref","unstructured":"Bartz C, Yang H, Meinel C (2018) SEE: towards semi-supervised end-to-end scene text recognition. In: Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12242"},{"issue":"11","key":"20913_CR14","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi B, Bai X, Yao C (2016) An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans Pattern Anal Mach Intell 39(11):2298\u20132304","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20913_CR15","doi-asserted-by":"crossref","unstructured":"Zhou X et al (2017) East: an efficient and accurate scene text detector. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5551\u20135560","DOI":"10.1109\/CVPR.2017.283"},{"key":"20913_CR16","doi-asserted-by":"crossref","unstructured":"Baek J et al (2019) What is wrong with scene text recognition model comparisons? dataset and model analysis. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4715\u20134723","DOI":"10.1109\/ICCV.2019.00481"},{"key":"20913_CR17","unstructured":"Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K (2015) Spatial transformer networks. In: Advances in neural information processing systems, vol 28. Available at: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2015\/hash\/33ceb07bf4eeb3da587e268d663aba1a-Abstract.html"},{"key":"20913_CR18","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"20913_CR19","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"20913_CR20","doi-asserted-by":"crossref","unstructured":"Liang M, Hu X (2015) Recurrent convolutional neural network for object recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3367\u20133375","DOI":"10.1109\/CVPR.2015.7298958"},{"key":"20913_CR21","doi-asserted-by":"crossref","unstructured":"Cheng Z, Bai F, Xu Y, Zheng G, Pu S, Zhou S (2017) Focusing attention: Towards accurate text recognition in natural images. In: Proceedings of the IEEE international conference on computer vision, pp 5076\u20135084","DOI":"10.1109\/ICCV.2017.543"},{"key":"20913_CR22","doi-asserted-by":"crossref","unstructured":"Shi B, Wang X, Lyu P, Yao C, Bai X (2016) Robust scene text recognition with automatic rectification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4168\u20134176","DOI":"10.1109\/CVPR.2016.452"},{"key":"20913_CR23","doi-asserted-by":"crossref","unstructured":"Graves A, Fern\u00e1ndez S, Gomez F, Schmidhuber J (2006) Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd international conference on machine learning, pp 369\u2013376","DOI":"10.1145\/1143844.1143891"},{"key":"20913_CR24","doi-asserted-by":"crossref","unstructured":"Kim S, Hori T, Watanabe S (2017) Joint CTC-attention based end-to-end speech recognition using multi-task learning. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 4835\u20134839","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"20913_CR25","doi-asserted-by":"publisher","unstructured":"Rainarli E, Suprapto, Wahyono (2021) A decade: Review of scene text detection methods. Comput Sci Rev 42:100434. https:\/\/doi.org\/10.1016\/j.cosrev.2021.100434","DOI":"10.1016\/j.cosrev.2021.100434"},{"key":"20913_CR26","doi-asserted-by":"crossref","unstructured":"Mishra A, Alahari K, Jawahar CV (2012) Scene text recognition using higher order language priors. In: BMVC-British machine vision conference. BMVA","DOI":"10.5244\/C.26.127"},{"key":"20913_CR27","unstructured":"Wang K, Babenko B, Belongie S (2011) End-to-end scene text recognition. In: 2011 International conference on computer vision. IEEE, pp 1457\u20131464"},{"key":"20913_CR28","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s10032-004-0134-3","volume":"7","author":"SM Lucas","year":"2005","unstructured":"Lucas SM et al (2005) ICDAR 2003 robust reading competitions: entries, results, and future directions. IJDAR 7:105\u2013122","journal-title":"IJDAR"},{"key":"20913_CR29","doi-asserted-by":"crossref","unstructured":"Karatzas D et al (2013) ICDAR 2013 robust reading competition. In: 2013 12th international conference on document analysis and recognition. IEEE, pp 1484\u20131493","DOI":"10.1109\/ICDAR.2013.221"},{"key":"20913_CR30","doi-asserted-by":"crossref","unstructured":"Smith R et al (2016) End-to-end interpretation of the french street name signs dataset. In: Computer Vision\u2013ECCV 2016 workshops: Amsterdam, The Netherlands, October 8\u201310 and 15\u201316, 2016, Proceedings, Part I 14. Springer, pp 411\u2013426","DOI":"10.1007\/978-3-319-46604-0_30"},{"key":"20913_CR31","doi-asserted-by":"crossref","unstructured":"Karatzas D et al (2015) ICDAR 2015 competition on robust reading. In: 2015 13th international conference on document analysis and recognition (ICDAR). IEEE, pp 1156\u20131160","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"20913_CR32","doi-asserted-by":"crossref","unstructured":"Phan TQ, Shivakumara P, Tian S, Tan CL (2013) Recognizing text with perspective distortion in natural scenes. In: Proceedings of the IEEE international conference on computer vision, pp 569\u2013576","DOI":"10.1109\/ICCV.2013.76"},{"issue":"18","key":"20913_CR33","doi-asserted-by":"publisher","first-page":"8027","DOI":"10.1016\/j.eswa.2014.07.008","volume":"41","author":"A Risnumawan","year":"2014","unstructured":"Risnumawan A, Shivakumara P, Chan CS, Tan CL (2014) A robust arbitrary text detection system for natural scene images. Expert Syst Appl 41(18):8027\u20138048","journal-title":"Expert Syst Appl"},{"key":"20913_CR34","unstructured":"Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2014) Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227"},{"key":"20913_CR35","doi-asserted-by":"crossref","unstructured":"Gupta A, Vedaldi A, Zisserman A (2016) Synthetic data for text localisation in natural images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2315\u20132324","DOI":"10.1109\/CVPR.2016.254"},{"key":"20913_CR36","unstructured":"Persian-OCR-Dataset. [Online]. Available: https:\/\/www.kaggle.com\/datasets\/amir137825\/persianocrdataset. Accessed 11 Apr 2023"},{"key":"20913_CR37","unstructured":"GitHub - heartexlabs\/labelImg: LabelImg is a graphical image annotation tool and label object bounding boxes in images. GitHub. [Online]. Available: https:\/\/github.com\/heartexlabs\/labelImg. Accessed 9 Sep 2022"},{"key":"20913_CR38","unstructured":"\u201cTABNAK\u2019\u2019. [Online]. Available: https:\/\/www.tabnak.ir\/. Accessed 13 Apr 2023"},{"key":"20913_CR39","unstructured":"Hazm (2023) Python. Roshan. [Online]. Available: https:\/\/github.com\/roshan-research\/hazm. Accessed 13 Apr 2023"},{"issue":"7","key":"20913_CR40","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova A et al (2020) The open images dataset V4. Int J Comput Vis 128(7):1956\u20131981. https:\/\/doi.org\/10.1007\/s11263-020-01316-z","journal-title":"Int J Comput Vis"},{"key":"20913_CR41","unstructured":"Zeiler MD (2012) ADADELTA: An adaptive learning rate method. arXiv preprint arXiv:1212.5701. Available at: https:\/\/arxiv.org\/abs\/1212.5701"},{"key":"20913_CR42","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu J et al (2018) Recent advances in convolutional neural networks. Pattern Recogn 77:354\u2013377","journal-title":"Pattern Recogn"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-20913-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-025-20913-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-20913-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T22:34:41Z","timestamp":1765319681000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-025-20913-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":42,"journal-issue":{"issue":"36","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["20913"],"URL":"https:\/\/doi.org\/10.1007\/s11042-025-20913-z","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2025,6,4]]},"assertion":[{"value":"16 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"All participants involved in this study were informed about the purpose, procedures, and their rights as participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"All participants provided explicit consent to publish their data in this study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publish"}},{"value":"The authors declare that they have no competing interests.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}